• International Journal of Naval Architecture and Ocean Engineering
• /
• v.11 no.1
• /
• pp.44-51
• /
• 2019

Designing sophisticate ship structures that satisfy several design criteria simultaneously with minimum weight and cost is an important engineering issue. For a ship structure composed of a shell and stiffeners, this issue is more serious because their mutual effect has to be addressed. In this study, a two-stage optimization method is proposed for the conceptual design of stiffeners in a ship's prow. In the first stage, a topology optimization method is used to determine a potential stiffener distribution based on the optimal results, whereupon stiffeners are constructed according to stiffener generative theory and the material distribution. In the second stage, size optimization is conducted to optimize the plate and stiffener sections simultaneously based on a parametric model. A final analysis model of the ship-prow structure is presented to assess the validity of this method. The analysis results show that the two-stage optimization method is effective for stiffener conceptual design, which provides a reference for designing actual stiffeners for ship hulls.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.3
• /
• pp.877-893
• /
• 2022

With the development of deep learning, face inpainting has been significantly enhanced in the past few years. Although image inpainting framework integrated with generative adversarial network or attention mechanism enhanced the semantic understanding among facial components, the issues of reconstruction on corrupted regions are still worthy to explore, such as blurred edge structure, excessive smoothness, unreasonable semantic understanding and visual artifacts, etc. To address these issues, we propose a Learnable Structure Knowledge of Fusion Network (LSK-FNet), which learns a prior knowledge by edge generation network for image inpainting. The architecture involves two steps: Firstly, structure information obtained by edge generation network is used as the prior knowledge for face inpainting network. Secondly, both the generated prior knowledge and the incomplete image are fed into the face inpainting network together to get the fusion information. To improve the accuracy of inpainting, both of gated convolution and region normalization are applied in our proposed model. We evaluate our LSK-FNet qualitatively and quantitatively on the CelebA-HQ dataset. The experimental results demonstrate that the edge structure and details of facial images can be improved by using LSK-FNet. Our model surpasses the compared models on L1, PSNR and SSIM metrics. When the masked region is less than 20%, L1 loss reduce by more than 4.3%.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.1
• /
• pp.80-96
• /
• 2022

Nowadays, artificial intelligence promotes the rapid development of skin cancer detection technology, and the federated skin cancer detection model (FSDM) and dual generative adversarial network model (DGANM) solves the fragmentation and privacy of data to a certain extent. To overcome the problem that the many-objective evolutionary algorithm (MaOEA) cannot guarantee the convergence and diversity of the population when solving the above models, a many-objective evolutionary algorithm based on integrated strategy (MaOEA-IS) is proposed. First, the idea of federated learning is introduced into population mutation, the new parents are generated through sub-populations employs different mating selection operators. Then, the distance between each solution to the ideal point (SID) and the Achievement Scalarizing Function (ASF) value of each solution are considered comprehensively for environment selection, meanwhile, the elimination mechanism is used to carry out the select offspring operation. Eventually, the FSDM and DGANM are solved through MaOEA-IS. The experimental results show that the MaOEA-IS has better convergence and diversity, and it has superior performance in solving the FSDM and DGANM. The proposed MaOEA-IS provides more reasonable solutions scheme for many scholars of skin cancer detection and promotes the progress of intelligent medicine.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.100-100
• /
• 2023

단기 강우 예측에는 주로 물리과정 기반 수치예보모델(NWPs, Numerical Prediction Models) 과 레이더 기반 확률론적 방법이 사용되어 왔으며, 최근에는 머신러닝을 이용한 레이더 기반 강우예측 모델이 단기 강우 예측에 뛰어난 성능을 보이는 것을 확인하여 관련 연구가 활발히 진행되고 있다. 하지만 머신러닝 기반 모델은 예측 선행시간 증가 시 성능이 크게 저하되며, 또한 대기의 물리적 과정을 고려하지 않는 Black-box 모델이라는 한계점이 존재한다. 본 연구에서는 이러한 한계를 극복하기 위해 머신러닝 기반 blending 기법을 통해 물리과정 기반 수치예보모델인 Weather Research and Forecasting (WRF)와 최신 머신러닝 기법 (cGAN, conditional Generative Adversarial Network) 기반 모델을 결합한 Hybrid 강우예측모델을 개발하고자 하였다. cGAN 기반 모델 개발을 위해 1시간 단위 1km 공간해상도의 레이더 반사도, WRF 모델로부터 산출된 기상 자료(온도, 풍속 등), 유역관련 정보(DEM, 토지피복 등)를 입력 자료로 사용하여 모델을 학습하였으며, 모델을 통해 물리 정보 및 머신러닝 기반 강우 예측을 생성하였다. 이렇게 생성된cGAN 기반 모델 결과와 WRF 예측 결과를 결합하는 머신러닝 기반 blending 기법을 통해Hybrid 강우예측 결과를 최종적으로 도출하였다. 본 연구에서는 Hybrid 강우예측 모델의 성능을 평가하기 위해 수도권 및 안동댐 유역에서 발생한 호우 사례를 기반으로 최대 선행시간 6시간까지 모델 예측 결과를 분석하였다. 이를 통해 물리과정 기반 모델과 머신러닝 기반 모델을 결합하는 Hybrid 기법을 적용하여 높은 정확도와 신뢰도를 가지는 고해상도 강수 예측 자료를 생성할 수 있음을 확인하였다.

• Annual Conference on Human and Language Technology
• /
• 2022.10a
• /
• pp.88-91
• /
• 2022

디지털 휴먼, 민원 상담, ARS 등 칫챗의 활용과 수요가 증가함에 따라 칫챗의 성능 향상을 위한 다양한 연구가 진행되고 있다. 특히, 오토 인코더(Auto-encoder) 기반의 생성 모델(Generative Model)은 높은 성능을 보이며 지속적인 연구가 이루어지고 있으나, 이전 대화들에 대한 충분한 문맥 정보의 반영이 어렵고 문법적으로 부적절한 답변을 생성하는 문제가 있다. 이를 개선하기 위해 검색 기반의 생성 모델과 관련된 연구가 진행되고 있으나, 현재 시점의 문장이 유사해도 이전 문장들에 따라 의도와 답변이 달라지는 멀티턴 대화 특징을 반영하여 대화를 검색하는 연구가 부족하다. 본 논문에서는 이와 같은 멀티턴 대화의 특징이 고려된 검색 방법을 제안하고 검색된 레퍼런스(준정답 문장)를 멀티턴 대화와 함께 생성 모델의 입력으로 활용하여 학습시키는 방안을 제안한다. 제안 방안으로 학습된 발화 생성 모델은 기존 모델과 비교 평가를 수행하며 Rouge-1 스코어에서 13.11점, Rouge-2 스코어에서 10.09점 Rouge-L 스코어에서 13.2점 향상된 성능을 보였고 이를 통해 제안 방안의 우수성을 입증하였다.

• Annual Conference on Human and Language Technology
• /
• 2023.10a
• /
• pp.716-721
• /
• 2023

Inverse Text Normalization(ITN) 모델은 음성 인식(STT) 엔진의 중요한 후처리 영역 중 하나이며, STT 인식 결과의 가독성을 개선한다. 최근 ITN 모델에 심층신경망을 활용한 연구가 진행되고 있다. 심층 신경망을 사용하는 대부분의 선행연구는 문장 내 변환이 필요한 부분에 토큰 태깅을 진행하는 방식이다. 그러나 이는 Out-of-vocabulary(OOV) 이슈가 있으며, 학습 데이터 구축 시 토큰 단위의 섬세한 태깅 작업이 필요하다는 한계점이 존재한다. 더불어 선행 연구에서는 STT 인식 결과를 그대로 사용하는데, 이는 띄어쓰기가 중요한 한국어 ITN 처리에 변환 성능을 보장할 수 없다. 본 연구에서는 BART 기반 생성 모델로 생성형 ITN 모델을 구축하였고, Bi-LSTM 기반 보조 신경망 모델을 결합하여 STT 인식 결과에 대한 고유명사 처리, 띄어쓰기 교정 기능을 보완한 모델을 제안한다. 또한 보조 신경망을 통해 생성 모델 처리 여부를 판단하여 평균 추론 속도를 개선하였다. 실험을 통해 두 모델의 각 정량 성능 지표에서 우수한 성능을 확인하였고 결과적으로 본 연구에서 제안하는 두 모델의 결합된 방법론의 효과성을 제시하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.908-909
• /
• 2023

Recently, several generative models have emerged and are being used in various industries. Among them, Cycle GAN is still used in various fields such as style transfer, medical care and autonomous driving. In this paper, we propose two methods to improve the performance of these Cycle GAN model. The ReLU activation function previously used in the generator was changed to Leaky ReLU. And a new loss function is proposed that considers the semantic level rather than focusing only on the pixel level through the VGG feature extractor. The proposed model showed quality improvement on the test set in the art domain, and it can be expected to be applied to other domains in the future to improve performance.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.47 no.6
• /
• pp.1137-1156
• /
• 2023

With the advent of artificial intelligence (AI) during the Fourth Industrial Revolution, the fashion industry has simplified the production process and overcome the technical difficulties of design. This study anticipates likely changes in the digital age and develops a model that will allow consumers to design textile patterns using AI technology. Previous studies and industrial examples of AI technology's use in the textile design industry were investigated, and a textile pattern was developed using an AI algorithm. A new textile design model was then proposed based on its application to both virtual and physical clothing. Inspired by traditional Korean masks and props, AI technology was used to input color data from open application programming interface images. By inserting these into various repeating structures, a textile design was developed and simulated as garments for both virtual and real garments. We expect that this study will establish a new textile design development method for Generation Z, who favor customized designs. This study can inform the use of personalization in generative textile design as well as the systemization of technology-driven methods for customized and participatory textile design.

• The Bulletin of The Korean Astronomical Society
• /
• v.46 no.1
• /
• pp.41.2-41.2
• /
• 2021

In this study, we generate He I 1083 nm images from Solar Dynamic Observatory (SDO)/Atmospheric Imaging Assembly (AIA) images using a novel deep learning method (pix2pixHD) based on conditional Generative Adversarial Networks (cGAN). He I 1083 nm images from National Solar Observatory (NSO)/Synoptic Optical Long-term Investigations of the Sun (SOLIS) are used as target data. We make three models: single input SDO/AIA 19.3 nm image for Model I, single input 30.4 nm image for Model II, and double input (19.3 and 30.4 nm) images for Model III. We use data from 2010 October to 2015 July except for June and December for training and the remaining one for test. Major results of our study are as follows. First, the models successfully generate He I 1083 nm images with high correlations. Second, the model with two input images shows better results than those with one input image in terms of metrics such as correlation coefficient (CC) and root mean squared error (RMSE). CC and RMSE between real and AI-generated ones for the model III with 4 by 4 binnings are 0.84 and 11.80, respectively. Third, AI-generated images show well observational features such as active regions, filaments, and coronal holes. This work is meaningful in that our model can produce He I 1083 nm images with higher cadence without data gaps, which would be useful for studying the time evolution of chromosphere and coronal holes.

• Journal of Intelligence and Information Systems
• /
• v.29 no.3
• /
• pp.401-418
• /
• 2023

Recently, the socio-economic interest in Large Language Models (LLMs) has been growing due to the emergence of ChatGPT. As a type of generative AI, LLMs have reached the level of script creation. In this regard, it is important to address the issue of discrimination (sexism, racism, religious discrimination, ageism, etc.) in the performing arts in general or in specific performing arts works or organizations in a large language model that will be widely used by the general public and professionals. However, there has not yet been a full-scale investigation and discussion on the issue of discrimination in the performing arts in large-scale language models. Therefore, the purpose of this study is to textually analyze the perceptions of discrimination issues in the performing arts from LMMs and to derive implications for the performing arts field and the development of LMMs. First, BBQ (Bias Benchmark for QA) questions and measures for nine discrimination issues were used to measure the sensitivity to discrimination of the giant language models, and the answers derived from the representative giant language models were verified by performing arts experts to see if there were any parts of the giant language models' misperceptions, and then the giant language models' perceptions of the ethics of discriminatory views in the performing arts field were analyzed through the content analysis method. As a result of the analysis, implications for the performing arts field and points to be noted in the development of large-scale linguistic models were derived and discussed.